-
1.发明公开公开(公告)号：US20240322941A1
公开(公告)日：2024-09-26
申请号：US18573914
申请日：2021-06-23
Applicant: LG Electronics Inc.
Inventor： Kijun JEON , Sangrim LEE , Hojae LEE , Yeongjun KIM , Taehyun LEE
IPC: H04L1/00
CPC classification number: H04L1/0041 , H04L1/0061
Abstract: The present disclosure provides a method for performing federated learning by one user equipment (UE) with a plurality of user equipments (UEs) in a wireless communication system. More specifically, the method performed by one UE comprises receiving, from a base station, restriction information related to an order restriction for an information field for generating a local parameter transmitted by the one UE to perform the federated learning; performing encoding on the local parameter generated from an order restricted information field based on the restriction information, wherein the encoded local parameter consists of a systematic bit part and a parity part; performing modulation on the encoded local parameter, wherein the modulation is performed in different ways for each of the systematic bit part and the parity part; and transmitting, to the base station, a signal including the modulated local parameters.
-
2.发明公开公开(公告)号：US20240031786A1
公开(公告)日：2024-01-25
申请号：US18025977
申请日：2020-09-15
Applicant: LG ELECTRONICS INC.
Inventor： Ikjoo JUNG , Sangrim LEE , JaYeong KIM , Yeongjun KIM , Sungjin KIM
CPC classification number: H04W4/40 , H04W56/001
Abstract: A method for performing reinforcement learning by a V2X communication device in an autonomous driving system, specifically, a method for performing reinforcement learning in consideration of a reward application ratio over time, is proposed. Action information is transmitted to a second V2X communication device, reward information is received from the second V2X communication device, and reinforcement learning is performed on the basis of a reward, wherein a reward corresponding to a ratio determined by a first V2X communication device is applied to the reinforcement learning, the ratio is determined on the basis of a time interval from a time point of transmission of the action information to a time point of reception of the reward information, and the ratio is between 0 and 1, both inclusive.
-
3.发明公开公开(公告)号：US20230327728A1
公开(公告)日：2023-10-12
申请号：US18024962
申请日：2020-09-07
Applicant: LG ELECTRONICS INC.
Inventor： Kijun JEON , Sangrim LEE , Hojae LEE , Yeongjun KIM , Sungjin KIM
IPC: H04B7/06
CPC classification number: H04B7/0626 , H04B7/0634
Abstract: Disclosed is a method for aligning gradient symbols by using bias regarding AirComp in a signal amplitude range of a receiver. A method for aligning gradient symbols according to an embodiment of the present disclosure comprises the steps of: performing iteration of gradient values included in a first planar vector and applying clipping and bias values so as to obtain a second planar vector having gradient values in which symbols are aligned; and transmitting the second planar vector together with channel information to a server in the form of AirComp. Various embodiments of the present disclosure may be linked to an artificial intelligence module, a drone (unmanned aerial vehicle, UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to a 5G service, and the like.
-
公开(公告)号：US20240106507A1
公开(公告)日：2024-03-28
申请号：US18265109
申请日：2020-12-04
Applicant: LG Electronics Inc.
Inventor： Hojae LEE , Sangrim LEE , Kyungho LEE , Yeongjun KIM , Kijun JEON , Sungjin KIM
IPC: H04B7/06 , H04B17/391
CPC classification number: H04B7/0626 , H04B7/0632 , H04B7/0639 , H04B17/3913
Abstract: The present specification provides a method fir transmitting learning class information, the method being performed by a terminal in a wireless communication system and comprising the steps of transmitting a random access (RA) preamble to a base station; receiving a random access response (RAR) from the base station in response to the RA preamble; performing a radio resource control (RRC) connection procedure with the base station; determining the learning class information, wherein the learning class information is information about the degree of performance improvement in online learning, and the online learning is artificial intelligence (AI) algorithm-based learning following the activation of the wireless communication system; transmitting the learning class information to the base station; and performing channel state information (CSI) feedback according to the learning class information.
-
公开(公告)号：US20230300895A1
公开(公告)日：2023-09-21
申请号：US18023127
申请日：2020-08-24
Applicant: LG Electronics Inc.
Inventor： Yeongjun KIM , Kijun JEON , Kyungho LEE , Sangrim LEE , Sungjin KIM
CPC classification number: H04W74/0833 , H04W76/10 , H04W74/006
Abstract: The present specification discloses a method and device. The method, which is for transmitting side information in a wireless communication system and performed by a terminal, comprises the steps of: transmitting a random access (RA) preamble to a base station; receiving a random access response (RAR) from the base station; performing a radio resource control (RRC) connection procedure with the base station; and establishing a digital transmission link with the base station, wherein the terminal acquires local gradient information about at least one resource, acquires side information from the local gradient information, and transmits the side information to the base station via the digital transmission link.
-
Patent Agency Ranking
公开(公告)号：US20220166490A1
公开(公告)日：2022-05-26
申请号：US17434786
申请日：2020-01-15
Applicant: LG Electronics Inc.
Inventor： Yeongjun KIM , Youngdae KIM
IPC: H04B7/08
Abstract: Disclosed in various embodiments are: a method by which user equipment (UE) performs beam sweeping by using a plurality of transmission beams in a wireless communication system for supporting a sidelink; and a device therefor. Particularly, disclosed in various embodiments are a method and a device therefor, the method comprising the steps of: receiving configuration information related to the beam sweeping; grouping the plurality of transmission beams into a plurality of groups on the basis of the number of reference beams included in the configuration information; and performing beam sweeping according to a transmission order determined for the plurality of groups, wherein the transmission order is determined on the basis of a group index for the plurality of groups and the number of repetitions in which the beam sweeping is repeatedly performed.
-
公开(公告)号：US20250106120A1
公开(公告)日：2025-03-27
申请号：US18728340
申请日：2022-01-13
Applicant: LG ELECTRONICS INC.
Inventor： Yeongjun KIM , Sangrim LEE , Bonghoe KIM , Kyungho LEE
Abstract: A reception device may perform end-to-end training in a wireless communication system. The reception device may: receive transmission neural network information including configuration of a transmission neural network from a transmission device; receive a plurality of training symbols for the transmission neural network from the transmission device; determine a gradient for the transmission neural network on the basis of the transmission neural network information and the plurality of training symbols; and feed the gradient back to the transmission device.
-
公开(公告)号：US20240414746A1
公开(公告)日：2024-12-12
申请号：US18702691
申请日：2022-10-17
Applicant: LG ELECTRONICS INC.
Inventor： Taehyun LEE , Sangrim LEE , Kijun JEON , Ikjoo JUNG , Yeongjun KIM
Abstract: The present disclosure provides a device and method for performing, based on channel information, a device grouping for federated learning based AirCOMP of a non-IID data environment in a communication system. The present disclosure also provides a device and method for performing effective federated learning in a non-IID environment including multiple devices. The present disclosure also provides a device and method for performing a device grouping in consideration of channel environment factors in order to apply AirComp based federated learning to a real communication environment.
-
公开(公告)号：US20230422308A1
公开(公告)日：2023-12-28
申请号：US18030800
申请日：2020-10-15
Applicant: LG ELECTRONICS INC.
Inventor： Sangrim LEE , Hojae LEE , Yeongjun KIM , Kijun JEON , Sungjin KIM
CPC classification number: H04W74/0833 , G06N3/098
Abstract: A superposition-based method for transmitting and receiving signals in wireless communication is provided. Provided is a signal reception method performed by a base station which performs federated machine-learning in a wireless communication system, the signal reception method comprising the steps of: receiving an aggregated signal; demodulating the aggregated signal; and decoding the aggregated signal, wherein the decoding is performed on the basis of a codebook combining the respective codebooks of a plurality of terminals, the aggregated signal is obtained by superposition, on a wireless channel, of signals respectively transmitted from the plurality of terminals, and the respective signals include information about neural network parameters related to the federated machine-learning respectively performed by the plurality of terminals.
-
公开(公告)号：US20230397018A1
公开(公告)日：2023-12-07
申请号：US18030726
申请日：2020-10-15
Applicant: LG ELECTRONICS INC.
Inventor： Sangrim LEE , Hojae LEE , Yeongjun KIM , Kijun JEON , Sungjin KIM
CPC classification number: H04W24/02 , H04W74/0833 , H04W74/006
Abstract: A signal transmission method performed by means of a terminal for performing federated learning in a wireless communication system is provided. According to the signal transmission method, the terminal receives downlink control information (DCI) from a base station, the DCI informing of a specific computation group ID and a modulation and coding scheme (MCS), modulates and encodes data on the basis of the MCS when the specific computation group ID is the same as a computation group ID allocated to the terminal, the data including a parameter related to the federated learning performed by the terminal, and transmits a signal including the data to the base station on the basis of the modulation and encoding.
-
-
-
-
-
-
-
-
-
Search Results
23
records
(took 0.015 seconds)
